Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130228
    Prev
    Next
    INDEX
    Explanations

    guessing game

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unavailable
    -0.08
     geselect
    -0.08
     passage
    -0.07
     precedent
    -0.07
     inactive
    -0.07
     involving
    -0.07
    wys
    -0.07
     membre
    -0.07
    _MEMBER
    -0.07
     southeast
    -0.07
    POSITIVE LOGITS
     guesses
    0.17
    猜
    0.16
     guessing
    0.15
    _guess
    0.14
     уга
    0.13
     guess
    0.13
    猜你
    0.13
     कोशिश
    0.13
    Attempts
    0.13
     attempts
    0.13
    Activations Density 0.010%

    No Known Activations